Researchers at Imperial College London and Imperial College Healthcare NHS Trust have developed an AI-enabled stethoscope capable of detecting heart failure, atrial fibrillation, and valve disease in just 15 seconds, as reported in BMJ Journals. This innovation, part of the TRICORDER study, could significantly improve patient outcomes by enabling earlier diagnosis and treatment of these conditions. The AI tool analyzes data from over 1.5 million patients, identifying heart failure with twice the accuracy compared to traditional methods. While promising, experts caution against routine use in healthy individuals due to potential false positives.
According to the British Heart Foundation (BHF), which partially funded the study, the researchers analyzed data from more than 1.5 million patients, focusing on individuals with heart failure symptoms like breathlessness, swelling, and fatigue. A total of 12,725 patients were examined using the new AI stethoscope technology, resulting in a diagnosis of heart failure for twice as many patients compared to similar patients not examined with the tool. Patients examined with the stethoscope were also about 3.5 times more likely to be diagnosed with atrial fibrillation, a condition that increases the risk of stroke. AI stethoscope users were also twice as likely to receive a heart valve disease diagnosis, where one or more valves work improperly.
All three of these conditions require early diagnosis to receive potentially life-saving treatment, according to the BHF press release. Dr. Patrik Bächtiger, a clinical lecturer at Imperial College London, noted in a statement that the design of the stethoscope, which was developed in 1816, has not changed in 200 years. He emphasized that the AI-enabled device can quickly deliver a test result indicating whether someone has heart failure, atrial fibrillation, or heart valve disease. Dr. Sonya Babu-Narayan, clinical director at the British Heart Foundation and consultant cardiologist, also commented that these heart conditions are often diagnosed at advanced stages when patients arrive at the hospital for emergency care. She stated that earlier diagnosis could allow patients to access the treatment they need to live well for longer.
The AI stethoscope, which is only about the size of a playing card, takes an ECG recording of the electrical signals from the patient’s heart. The microphone on the tool also records the sound of blood flowing through the heart. The recorded information is analyzed by AI algorithms trained on health data from tens of thousands of people, generating a test result for heart failure risk. A separate algorithm can detect atrial fibrillation, which often shows no symptoms. Researchers suggest that there needs to be more integration of the technology into general practice, as 70% of practitioners with smart stethoscopes stopped using them after 12 months. The study also found that two-thirds of people who were suspected to have heart failure were found not to have the condition after a further blood test or heart scan.
The BHF emphasized that the AI stethoscope should be used for patients with symptoms of suspected heart problems rather than for routine checks in healthy people. In a recent interview with Fox News Digital, cardiothoracic surgeon Dr. Jeremy London commented on the emergence of AI in medicine. ‘Deciding which protocol is the science of medicine; whether or not that protocol is actually appropriate for that patient is the art of medicine,’ he said. ‘And with AI, there isn’t a human quality to that at this point, so figuring out how to interface those two is a real challenge.’ London emphasized the need to use AI as ‘a framework, not as an absolute, because it can be wrong.’ He believes that in the long term, AI will be ‘more beneficial than detrimental’ in medicine.